ABSTRACT
ObjectiveIn view of the standardization of clinical diagnosis and treatment of the acute abdomen and the inheritance of diagnosis and treatment experience of prestigious veteran traditional Chinese medicine（TCM） doctors， a diagnosis and treatment reasoning algorithm based on association rule mining under incomplete evidence（AMIE）+ random walk was proposed to provide information services and technical support for primary doctors by recommending personalized diagnosis and treatment plans based on medical records. MethodThe experience of diagnosis and treatment of acute abdomen of prestigious veteran TCM doctors and the text data of clinical diagnosis and treatment guidelines of integrated TCM and western medicine were collected to complete the task of knowledge extraction and construct acute abdomen knowledge graph based on Neo4j. On the basis of ontology-supported rule-based reasoning， the rule reasoning based on similar syndromes was used to expand the syndrome combinations whose Jaccard similarity was greater than the threshold in the syndrome recommendation results. The semantic path coverage algorithm was used to calculate the semantic similarity between the symptom nodes. The symptom nodes were divided into 10 categories， and the symptom nodes in the same category were extended. The random walk algorithm was used to search the symptom nodes connected with the syndrome， and the connection rules between the syndrome and symptom nodes were extended to realize the knowledge reasoning of AMIE+ random walk. ResultThe acute abdomen knowledge graph included 1 320 nodes and 2 464 relationships. According to the link prediction evaluation index of knowledge reasoning， the reasoning results of the three algorithms in the auxiliary diagnosis and treatment of acute abdomen were compared. The AMIE+ random walk algorithm complemented the knowledge graph by extending the similar syndrome connection rules and the syndrome-symptom connection rules. Compared with the knowledge reasoning algorithm based on ontology rules， the area under the curve （AUC） was 15.18% higher and the accuracy was 30.36% higher， which achieved more accurate and effective knowledge inference. ConclusionThis study used knowledge graph technology to visualize the diagnosis and treatment of acute abdomen with TCM and western medicine， assisting primary clinicians in intuitively viewing the diagnosis and treatment process and data relationship. The proposed diagnosis and treatment reasoning algorithm can realize the personalized diagnosis and treatment plan recommendation at the level of "disease-syndrome-diagnosis-treatment-prescription"， which can assist primary doctors in disease diagnosis and treatment and clinical decision-making， contribute to the knowledge sharing and application of diagnosis and treatment experience and clinical guidelines of prestigious veteran TCM doctors， improve the level of primary clinical diagnosis and treatment， and promote the normalization and standardization of the diagnosis and treatment process of acute abdomen with integrated TCM and western medicine.
ABSTRACT
In Japan, the National Health Insurance (NHI) prices of new drugs are set according to the NHI Drug Price Standard (NHI Price Standard). The NHI Price Standard was notified by the Ministry of Health, Labour, and Welfare based on the ”Drug Price Calculation Criteria” proposed by the Central Social Insurance Medical Council (Chuikyo) in Japan. The NHI Price Standard affects the research and development strategy of pharmaceutical companies. In order to discover undetected relationships, the factors influencing the ”drug price” were evaluated through the association rule mining technique. We surveyed the Chuikyo‐documents about NHI price listing over the period October 27, 2006 to February 8, 2007. The number of approved new drugs was 874, while that of drugs completed (”drug price per day”) was 314. The numbers of new compounds corresponding to a drug price per day of ”below 200 yen,” ”between 200 yen and 1,000 yen,” ”between 1,000 and 10,000 yen,” and ”above or equal to 10,000 yen” were 87 (27.7%), 91 (29.0%), 79 (25.2%), and 57 (18.2%), respectively. In the association rule mining method, we observed high lift values of the combined items ”above or equal to 30,000 patients expected to be administrated” and ”drugs affecting sensory organs” in the group of drug price per day below 200 yen. The lift values of the combinations of ”biological preparations” and ”similar efficacy comparison‐based price setting (Ⅱ)” or ”below 30,000 patients expected to be administrated” and ”antineoplastic drug” in the group of ”above or equal to 10,000 yen of drug price per day” were high. These results provide a basis for the development and application of new drugs in Japan.
ABSTRACT
Objective: To study the rule pattern of risk factor of stroke through data analysis of preliminary screening of large-scale stroke. Methods: The preliminary screening data of risk factors in stroke were gathered from the National Center for Stroke Screening and Prevention and Control. And the association rules mining was adopted in the research. The relevant risk factors of stroke in large-scale crowd were researched, and 0.1% was chose as minimum support and 10% were used as minimum confidence coefficient. The rule mode of stroke was mined by using above conditions. Results: In the nine risk factors of the table of preliminary screening, there was a weak correlation between "transient ischemic attack (TIA) in past", "hypertension", "family history of stroke" and stroke, respectively. And TIA, atrial fibrillation or valvular heart disease, family history of stroke, hypertension and diabetes were the most important risk factors. At the same time, the study found that age would become an important risk factor for stroke when patient was older than 60. Conclusions: In the 21 presumptive rule patterns with big probability, some of them has not received sufficient attention in past. And the rule pattern of risk factor of stroke provides a new diagnostic basis with value.
ABSTRACT
Data mining techniques are used in various areas like stock exchange, education, bioinformatics, health care etc. The main purpose of data mining techniques is used to extract the useful and interesting information. Association Rule Mining (ARM) associates the different attributes and gives the most suitable rules from large database. Protein ligand binding is an important step in enzymatic mechanisms and in drug discovery. This research work gives the association rules for amino acid residues which are present in the binding site of Alzheimer’s Disease Related Studies targets. The data are collected from Protein Data Bank. Association rule mining is applied in the Alzheimer’s Disease Related Studies protein and the interesting rules for the amino acid residues present in the Alzheimer’s Disease Related Studies are formed. Ile and Ser are the amino acid residues which are having major role in the precedence of association rules of Alzheimer’s Disease Related Studies. This research work may support in identify new binding protein-ligand pairs and predict protein ligand binding in particular diseases.